linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tong Tiangen <tongtiangen@huawei.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	David Howells <dhowells@redhat.com>, Al Viro <viro@kernel.org>,
	Jens Axboe <axboe@kernel.dk>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: <linux-fsdevel@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	Tong Tiangen <tongtiangen@huawei.com>,
	<wangkefeng.wang@huawei.com>, Guohanjun <guohanjun@huawei.com>
Subject: [PATCH] coredump: get machine check errors early rather than during iov_iter
Date: Tue, 5 Mar 2024 21:33:36 +0800	[thread overview]
Message-ID: <20240305133336.3804360-1-tongtiangen@huawei.com> (raw)

The commit f1982740f5e7 ("iov_iter: Convert iterate*() to inline funcs")
leads to deadloop in generic_perform_write()[1], due to return value of
copy_page_from_iter_atomic() changed from non-zero value to zero.

The code logic of the I/O performance-critical path of the iov_iter is
mixed with machine check[2], actually, there's no need to complicate it,
a more appropriate method is to get the error as early as possible in
the coredump process instead of during the I/O process. In addition,
the iov_iter performance-critical path can have clean logic.

[1] https://lore.kernel.org/lkml/4e80924d-9c85-f13a-722a-6a5d2b1c225a@huawei.com/
[2] commit 245f09226893 ("mm: hwpoison: coredump: support recovery from dump_user_range()")

Fixes: f1982740f5e7 ("iov_iter: Convert iterate*() to inline funcs")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Tong Tiangen <tongtiangen@huawei.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Tested-by: David Howells <dhowells@redhat.com>
---
 fs/coredump.c       | 42 +++++++++++++++++++++++++++++++++++++++---
 include/linux/uio.h | 16 ----------------
 lib/iov_iter.c      | 23 -----------------------
 3 files changed, 39 insertions(+), 42 deletions(-)

diff --git a/fs/coredump.c b/fs/coredump.c
index f258c17c1841..ea155ffee14c 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -872,6 +872,9 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	loff_t pos;
 	ssize_t n;
 
+	if (!page)
+		return 0;
+
 	if (cprm->to_skip) {
 		if (!__dump_skip(cprm, cprm->to_skip))
 			return 0;
@@ -884,7 +887,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	pos = file->f_pos;
 	bvec_set_page(&bvec, page, PAGE_SIZE, 0);
 	iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE);
-	iov_iter_set_copy_mc(&iter);
 	n = __kernel_write_iter(cprm->file, &iter, &pos);
 	if (n != PAGE_SIZE)
 		return 0;
@@ -895,10 +897,41 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page)
 	return 1;
 }
 
+/*
+ * If we might get machine checks from kernel accesses during the
+ * core dump, let's get those errors early rather than during the
+ * IO. This is not performance-critical enough to warrant having
+ * all the machine check logic in the iovec paths.
+ */
+#ifdef copy_mc_to_kernel
+
+#define dump_page_alloc() alloc_page(GFP_KERNEL)
+#define dump_page_free(x) __free_page(x)
+static struct page *dump_page_copy(struct page *src, struct page *dst)
+{
+	void *buf = kmap_local_page(src);
+	size_t left = copy_mc_to_kernel(page_address(dst), buf, PAGE_SIZE);
+
+	kunmap_local(buf);
+	return left ? NULL : dst;
+}
+
+#else
+
+#define dump_page_alloc() ((struct page *)8) // Not NULL
+#define dump_page_free(x) do { } while (0)
+#define dump_page_copy(src, dst) ((dst), (src))
+
+#endif
+
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len)
 {
 	unsigned long addr;
+	struct page *dump_page = dump_page_alloc();
+
+	if (!dump_page)
+		return 0;
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page;
@@ -912,14 +945,17 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		 */
 		page = get_dump_page(addr);
 		if (page) {
-			int stop = !dump_emit_page(cprm, page);
+			int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page));
 			put_page(page);
-			if (stop)
+			if (stop) {
+				dump_page_free(dump_page);
 				return 0;
+			}
 		} else {
 			dump_skip(cprm, PAGE_SIZE);
 		}
 	}
+	dump_page_free(dump_page);
 	return 1;
 }
 #endif
diff --git a/include/linux/uio.h b/include/linux/uio.h
index bea9c89922d9..00cebe2b70de 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -40,7 +40,6 @@ struct iov_iter_state {
 
 struct iov_iter {
 	u8 iter_type;
-	bool copy_mc;
 	bool nofault;
 	bool data_source;
 	size_t iov_offset;
@@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 
 #ifdef CONFIG_ARCH_HAS_COPY_MC
 size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
-static inline void iov_iter_set_copy_mc(struct iov_iter *i)
-{
-	i->copy_mc = true;
-}
-
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
-	return i->copy_mc;
-}
 #else
 #define _copy_mc_to_iter _copy_to_iter
-static inline void iov_iter_set_copy_mc(struct iov_iter *i) { }
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
-	return false;
-}
 #endif
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
@@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_UBUF,
-		.copy_mc = false,
 		.data_source = direction,
 		.ubuf = buf,
 		.count = count,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e0aa6b440ca5..cf2eb2b2f983 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -166,7 +166,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
-		.copy_mc = false,
 		.nofault = false,
 		.data_source = direction,
 		.__iov = iov,
@@ -244,27 +243,9 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
 #endif /* CONFIG_ARCH_HAS_COPY_MC */
 
-static __always_inline
-size_t memcpy_from_iter_mc(void *iter_from, size_t progress,
-			   size_t len, void *to, void *priv2)
-{
-	return copy_mc_to_kernel(to + progress, iter_from, len);
-}
-
-static size_t __copy_from_iter_mc(void *addr, size_t bytes, struct iov_iter *i)
-{
-	if (unlikely(i->count < bytes))
-		bytes = i->count;
-	if (unlikely(!bytes))
-		return 0;
-	return iterate_bvec(i, bytes, addr, NULL, memcpy_from_iter_mc);
-}
-
 static __always_inline
 size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
-	if (unlikely(iov_iter_is_copy_mc(i)))
-		return __copy_from_iter_mc(addr, bytes, i);
 	return iterate_and_advance(i, bytes, addr,
 				   copy_from_user_iter, memcpy_from_iter);
 }
@@ -633,7 +614,6 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_KVEC,
-		.copy_mc = false,
 		.data_source = direction,
 		.kvec = kvec,
 		.nr_segs = nr_segs,
@@ -650,7 +630,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter){
 		.iter_type = ITER_BVEC,
-		.copy_mc = false,
 		.data_source = direction,
 		.bvec = bvec,
 		.nr_segs = nr_segs,
@@ -679,7 +658,6 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction,
 	BUG_ON(direction & ~1);
 	*i = (struct iov_iter) {
 		.iter_type = ITER_XARRAY,
-		.copy_mc = false,
 		.data_source = direction,
 		.xarray = xarray,
 		.xarray_start = start,
@@ -703,7 +681,6 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
 	BUG_ON(direction != READ);
 	*i = (struct iov_iter){
 		.iter_type = ITER_DISCARD,
-		.copy_mc = false,
 		.data_source = false,
 		.count = count,
 		.iov_offset = 0
-- 
2.25.1


             reply	other threads:[~2024-03-05 13:33 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-03-05 13:33 Tong Tiangen [this message]
2024-03-05 13:58 ` [PATCH] coredump: get machine check errors early rather than during iov_iter Jens Axboe
2024-03-05 16:33 ` Christian Brauner
2024-03-05 16:39   ` Jens Axboe
2024-03-05 17:29     ` Linus Torvalds
2024-03-06  8:56       ` Christian Brauner
2024-03-06  8:56     ` Christian Brauner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240305133336.3804360-1-tongtiangen@huawei.com \
    --to=tongtiangen@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=brauner@kernel.org \
    --cc=dhowells@redhat.com \
    --cc=guohanjun@huawei.com \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=viro@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wangkefeng.wang@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).